Radon Transform for Lineal Symbol Representation

  • Authors:
  • Oriol Ramos Terrades;Ernest Valveny

  • Affiliations:
  • -;-

  • Venue:
  • ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

Content-based retrieval and recognition of graphic imagesrequires good models for symbol representation, ableto identify those features providing the most relevant informationabout the shape and the visual appearance of symbols.In this work we have used the Radon transform as thebasis to extract the representation of graphic images as itpermits to globally detect lineal singularities in an image,which are the most important source of information in theseimages. The image obtained after applying Radon transformcan be used directly to describe the symbol, or can beused to extract new and compact descriptors from it, whichwill also be based on lineal information about the image.We present some preliminary results showing the usefulnessof this representation with a set of architectural symbols.